Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 28360
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to computational complexity and modeling in systems biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ode
    -0.16
     ty
    -0.15
    odor
    -0.15
    ugu
    -0.14
    766
    -0.14
    à¤¾à¤ł
    -0.14
    udo
    -0.14
    ç¬
    -0.14
     carrier
    -0.14
    .kernel
    -0.14
    POSITIVE LOGITS
     hardness
    0.23
     membership
    0.19
    -hard
    0.18
    hard
    0.17
    orest
    0.17
     Reduction
    0.16
     reductions
    0.16
     Membership
    0.16
    membership
    0.16
    Membership
    0.16
    Activations Density 0.018%

    No Known Activations